Traditional information retrieval uses words as the basic representation units. It is known that such a representation has several problems, in particular, when dealing with synonymous and polysemous words. These problems are particularly important for information retrieval. A series of latent representations have been used to address the problems, ranging from LSA, LDA to more recent embeddings. In this talk, we will review these representations for IR applications. It will be shown that latent representations can help solve the problems to some extent, but cannot (yet) fully replace the traditional word-based representation. We will provide some analysis on this.

 

Jian-Yun Nie is a professor in University of Montreal. He obtained his PhD from University of Grenoble (France) on information retrieval. Since then, his research has always been focused on information retrieval and natural language processing. Among other topics, he has worked on IR models, cross-language IR, query expansion and query understanding. Jian-Yun Nie has published a number of papers on these topics and his papers have been widely cited. He published a monograph on cross-language information retrieval (Morgan and Claypool, 2010). He is on editorial board of several international journals, and is a regular PC member of the major conferences in these areas (SIGIR, CIKM, ACL, etc.). He has also been the general chair of SIGIR conference in 2011 held in Beijing.